• Journal of the Korea Computer Graphics Society
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2010

With the widespread use of vision-based surveillance systems, the capability for person identification is now an essential component. However, the CCTV cameras used in surveillance systems tend to produce relatively low-resolution images, making it difficult to use face recognition techniques for person identification. Therefore, an algorithm is proposed for person identification in CCTV camera images based on the clothing. Whenever a person is authenticated at the main entrance of a building, the clothing feature of that person is extracted and added to the database. Using a given image, the clothing area is detected using background subtraction and skin color detection techniques. The clothing feature vector is then composed of textural and color features of the clothing region, where the textural feature is extracted based on a local edge histogram, while the color feature is extracted using octree-based quantization of a color map. When given a query image, the person can then be identified by finding the most similar clothing feature from the database, where the Euclidean distance is used as the similarity measure. Experimental results show an 80% success rate for person identification with the proposed algorithm, and only a 43% success rate when using face recognition.

• Journal of KIISE:Software and Applications
• /
• v.37 no.6
• /
• pp.455-463
• /
• 2010

In this paper, we present an approach to sentence boundary detection for web documents that builds on statistical-based methods and uses rule-based correction. The proposed system uses the classification model learned offline using a training set of human-labeled web documents. The web documents have many word-spacing errors and frequently no punctuation mark that indicates the end of sentence boundary. As sentence boundary candidates, the proposed method considers every Ending Eomis as well as punctuation marks. We optimize engine performance by selecting the best feature, the best training data, and the best classification algorithm. For evaluation, we made two test sets; Set1 consisting of articles and blog documents and Set2 of web community documents. We use F-measure to compare results on a large variety of tasks, Detecting only periods as sentence boundary, our basis engine showed 96.5% in Set1 and 56.7% in Set2. We improved our basis engine by adapting features and the boundary search algorithm. For the final evaluation, we compared our adaptation engine with our basis engine in Set2. As a result, the adaptation engine obtained improvements over the basis engine by 39.6%. We proved the effectiveness of the proposed method in sentence boundary detection.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.1
• /
• pp.84-93
• /
• 2011

Levee line mapping is critical to the protection of environments in river zones, the prevention of river flood and the development of river zones. Use of the remote sensing data such as LiDAR and aerial orthoimage is efficient for river mapping due to their accessibility and higher accuracy in horizontal and vertical direction. Airborne laser scanning (LiDAR) has been used for river zone mapping due to its ability to penetrate shallow water and its high vertical accuracy. Use of image source is also efficient for extraction of features by analysis of its image source. Therefore, aerial orthoimage also have been used for river zone mapping tasks due to its image source and its higher accuracy in horizontal direction. Due to these advantages, in this paper, research on three dimensional levee line mapping is implemented using LiDAR and aerial orthoimage separately. Accuracy measurement is implemented for both extracted lines generated by each data using the ground truths and statistical comparison is implemented between two measurement results. Statistical results show that the generated 3D levee line using LiDAR data has higher accuracy than the generated 3D levee line using aerial orthoimage in horizontal direction and vertical direction.

• Journal of the Korea Convergence Society
• /
• v.8 no.12
• /
• pp.85-92
• /
• 2017

As accessibility toward traditional cultural contents drops compared to its increase in production, the need for higher accessibility for continued management and research to exist. For this, this paper introduces an image classifier model for traditional images based on artificial neural networks, which converts the input image's features into a vector space and by utilizing a RNN based model it recognizes and compares the details of the input which enables the classification of traditional images. This enables the classifiers to classify similarly looking traditional images more precisely by focusing on the details. For the training of this model, a wide range of images were arranged and collected based on the format of the Korean information culture field, which contributes to other researches related to the fields of using traditional cultural images. Also, this research contributes to the further activation of demand, supply, and researches related to traditional culture.

• Journal of Korea Multimedia Society
• /
• v.7 no.2
• /
• pp.173-186
• /
• 2004

This paper proposed the content-based retrieval system as a method for performing image retrieval through the effective feature extraction of the object of significant meaning based on the characteristics of man's visual system. To allow the object region of interest to be primarily detected, the region, being comparatively large size, greatly different from the background color and located in the middle of the image, was judged as the major object with a meaning. To get the original features of the image, the cumulative sum of tile declination difference vector the segment of the object contour had and the signature of the bipartite object were extracted and used in the form of being applied to the rotation of the object and the change of the size after partition of the total length of the object contour of the image into the normalized segment. Starting with this form feature, it was possible to make a retrieval robust to any change in translation, rotation and scaling by combining information on the texture sample, color and eccentricity and measuring the degree of similarity. It responded less sensitively to the phenomenon of distortion of the object feature due to the partial change or damage of the region. Also, the method of imposing a different weight of similarity on the image feature based on the relationship of complexity between measured objects using the fractal dimension by the Boxing-Counting Dimension minimized the wrong retrieval and showed more efficient retrieval rate.

• Journal of KIISE
• /
• v.42 no.3
• /
• pp.367-378
• /
• 2015

This study was directed at the design of a hybrid algorithm for competition relation extraction. Previous works on relation extraction have relied on various lexical and deep parsing indicators and mostly utilize only the machine learning method. We present a new algorithm integrating machine learning with various filtering methods. Some simple but useful features for competition relation extraction are also introduced, and an optimum feature set is proposed. The goal of this paper was to increase the precision of competition relation extraction by combining supervised learning with various filtering methods. Filtering methods were employed for classifying compete relation occurrence, using distance restriction for the filtering of feature pairs, and classifying whether or not the candidate entity pair is spam. For evaluation, a test set consisting of 2,565 sentences was examined. The proposed method was compared with the rule-based method and general relation extraction method. As a result, the rule-based method achieved positive precision of 0.812 and accuracy of 0.568, while the general relation extraction method achieved 0.612 and 0.563, respectively. The proposed system obtained positive precision of 0.922 and accuracy of 0.713. These results demonstrate that the developed method is effective for competition relation extraction.

• Journal of Broadcast Engineering
• /
• v.17 no.3
• /
• pp.519-528
• /
• 2012

Voice activity detection (VAD) is generally conducted by extracting features from the acoustic signal and a decision rule. The performance of such VAD algorithms driven by the input acoustic signal highly depends on the acoustic noise. When video signals are available as well, the performance of VAD can be enhanced by using the visual information which is not affected by the acoustic noise. Previous visual VAD algorithms usually use single visual feature to detect the lip activity, such as active appearance models, optical flow or intensity variation. Based on the analysis of the weakness of each feature, we propose to combine intensity change measure and the optical flow in the mouth region, which can compensate for each other's weakness. In order to minimize the computational complexity, we develop simple measures that avoid statistical estimation or modeling. Specifically, the optical flow is the averaged motion vector of some grid regions and the intensity variation is detected by simple thresholding. To extract the mouth region, we propose a simple algorithm which first detects two eyes and uses the profile of intensity to detect the center of mouth. Experiments show that the proposed combination of two simple measures show higher detection rates for the given false positive rate than the methods that use a single feature.

• Journal of Korea Multimedia Society
• /
• v.16 no.6
• /
• pp.764-781
• /
• 2013

In this paper, we propose a highly precise vehicle detection method with low false alarm using billboard sweep stereo matching and multi-stage hypothesis generation. First, we capture stereo images from cameras established in front of the vehicle and obtain the disparity map in which the regions of ground plane or background are removed using billboard sweep stereo matching algorithm. And then, we perform the vehicle detection and tracking on the labeled disparity map. The vehicle detection and tracking consists of three steps. In the learning step, the SVM(support vector machine) classifier is obtained using the features extracted from the gabor filter. The second step is the vehicle detection which performs the sobel edge detection in the image of the left camera and extracts candidates of the vehicle using edge image and billboard sweep stereo disparity map. The final step is the vehicle tracking using template matching in the next frame. Removal process of the tracking regions improves the system performance in the candidate region of the vehicle on the succeeding frames.

• Journal of the Korean association of regional geographers
• /
• v.15 no.2
• /
• pp.307-315
• /
• 2009

The purpose of map generalization is a method of map making to transmit the concise cartographic representation and geographic meaning. New generalization algorithm has been developed to be applied in the digital environments by the development of computer cartography. This study aims to look into possibilities of the multiscale mapping by generalization in application with the coordinate transformation and LoD(level of detail) in the web cartography. A method of the coordinate transformation is to improve a transmission of spatial data. Lod is a method which is making web map with selection spatial data by zoom level of users. Layers for test constructed contour line, stream network, the name of a place, a summit of mountain, and administrative office. The generalization was applied to zoom levels by scale for the linear and polygonal features using XML-Based scalable vector graphics(SVG). Resultantly, storage capacity of data was minimized 41% from 9.76mb to 4.08mb in SVG. Generalization of LoD was applied to map elements by stages of the zoom level. In the first stages of zoom level, the main name of places and administrative office, higher order of stream channels, main summit of mountain was represented, and become increase numbers of map elements in the higher levels. Results of this study can help to improve esthetic map and data minimization in web cartography, and also need to make an efforts to research an algorithm on the map generalization over the web.

• Journal of Preventive Medicine and Public Health
• /
• v.7 no.2
• /
• pp.403-415
• /
• 1974

The author has investigated epidemiological features of human cases of epidemic encephalitis (E. E.) in the Republic of Korea and the status of antibody requisition in pre-and post-epidemic time. And virological and serological studies with regarding the relationship of E. E. infection between human and piglet, and field survey against its vector by means of virus isolation from mosquitoes were carried out. Finally, vaccine field trial against human population has also been evaluated in order to confirm its effectiveness. The results of the studies are summarized as follows : 1. The annual incidence of reported cases during the past 25 years (1949-1973) in the Republic of Korea has shown two patterns, one was typical cyclic incidence and the other one was irregular. Annual average morbidity and mortality rate per 100,000 population were 5.7 and 2.1 and fatality rate was 34.6% in typical cyclic years. 2. With regard to the geographical distribution of E. E., the province of Jeolla-Bug-Do illustrated the highest incidence regardless of the epidemic size. 3. The main epidemic period was between mid-August and mid-September (above 90% of the total number of cases). The first case was reported in middle of July and the epidemic ceased in late of October. 4. An analysis of the age distribution of cases of E. E., has shown that above 90% of the total cases occurred in the age groups under 14 years and it was noted that about its 54% were occurred in the age groups between 5-9 years group. 5. Through the Haemagglutination Inhibition (H-I) test for the laboratory diagnosis of E. E., it was found that higher H-I antibody titer was usually detected in the convalescent phase, 15 days after onset. 6. The H-I antibody survey against 563 healthy population by age groups during the pre-epidemic season showed that 422(75%) were less than H-I titer, 1:20 and 122(21.7%) were positive H-I titer, 1:20. Among the 94 American in Seoul who had not been in E. E. endemic area previously only one person had appeared sero-conversion as a H-I titer of 1:80 after post-epidemic season. 7. The E. E. virus could be isolated from the mosquitos pools-C, tritaeniorhyncus which were caught between late July and middle August. 8. E.E. Virus was also isolated from piglet blood on early August and H-I antibody conversion was occurred mostly on middle of August. 9. H-I antibody sero-conversion rate reached to high level when vaccine purified by mouse brain tissue inoculated, showing 98.9%. Higher antibody titer was acquired when booster inoculation was performed, Four fold rise of H-I add N-T antibodies was confirmed with 93.2% and 82.1% respectively.